论文标题
深度展开磁共振指纹
Deep Unrolling for Magnetic Resonance Fingerprinting
论文作者
论文摘要
磁共振指纹（MRF）已成为一种有希望的定量MR成像方法。已经提出了针对MRF的深度学习方法，并证明了与经典压缩感测算法相比的性能改善。但是，这些端到端模型中的许多是不含物理的，而相对于物理前向模型的预测的一致性对于可靠地解决反问题至关重要。为了解决这个问题，最近[1]提出了一个近端梯度下降框架，该框架将正向采集和Bloch动态模型直接纳入了展开的学习机制。但是，[1]仅使用笛卡尔采样轨迹评估了合成数据上的独立模型。在本文中，作为对[1]的互补性，我们研究了编码器的其他选择以构建近端神经网络，并评估了使用非智力K空间采样轨迹的实际加速MRF扫描的深层展开算法。
Magnetic Resonance Fingerprinting (MRF) has emerged as a promising quantitative MR imaging approach. Deep learning methods have been proposed for MRF and demonstrated improved performance over classical compressed sensing algorithms. However many of these end-to-end models are physics-free, while consistency of the predictions with respect to the physical forward model is crucial for reliably solving inverse problems. To address this, recently [1] proposed a proximal gradient descent framework that directly incorporates the forward acquisition and Bloch dynamic models within an unrolled learning mechanism. However, [1] only evaluated the unrolled model on synthetic data using Cartesian sampling trajectories. In this paper, as a complementary to [1], we investigate other choices of encoders to build the proximal neural network, and evaluate the deep unrolling algorithm on real accelerated MRF scans with non-Cartesian k-space sampling trajectories.
